Learn More
Colorization is a computer-assisted process of adding color to a monochrome image or movie. Most current colorization algorithms either require a significant user effort or have large computational time. In any case, colorization of real size images remains a time-consuming, tedious task. In this paper we present a new colorization method, based on GrowCut(More)
We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. We chose an appropriate 3-d model structure and formulate the task of 3-d reconstruction as model fitting problem. Our 3-d models are composed of a number of vertical walls and a(More)
This paper presents an approach to fully automatic people tracking in surveillance video recorded by stable camera. We propose an improvement on Benfold et al. tracking-by-detection algorithm [1]. We extend the basic algorithm through filtering of person detector results and the scene entrance/exit positions construction. Moreover, the paper presents a(More)
Digital image matting is a process of extracting a foreground object from an arbitrary natural image. Unlike the image segmentation task it is required to process fuzzy objects (like hair, feathers, etc.) and produce correct opacity channel for them. The result can then be composited onto a new background or edited by processing foreground and background(More)
The image matting problem refers to foreground object extraction from an image. Similarly, video matting problem refers to extraction of a foreground object from each frame of a video-sequence producing a moving foreground layer. Layer extraction process should deal with the transparency caused by camera point spread function (PSF) and motion blur, thus the(More)
We present a new approach to face classification using simile classifiers. Unlike other methods we explicitly estimate similarity distances to the known reference people and use these similarities as high-level features for the classification of the test face. We test our algorithm on gender classification problem. Our algorithm shows classification(More)
  • 1